Vanegas D.

Key Skills

Software

AWS SageMaker

Other

Don't disclose

Top Subject Matter

Computational biology

peptide sequence classification and optimization

Healthcare analytics

Top Data Types

Text

Image

Top Task Types

Prompt + Response Writing (SFT)

Question Answering

Text Generation

Diagnosis

Classification

Object Detection

Freelancer Overview

Chief Computational Officer & Cofounder, Organicin Scientific (Part-time). Brings 16+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include AWS SageMaker, Other, and Don't disclose. Education includes Professional Certificate, Massachusetts Institute of Technology (2022) and Professional Certificate, Springboard (2023). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Prompt + Response Writing (SFT), Question Answering, and Text Generation.

Labeling Experience

Senior Scientist, Merck (Hybrid)

OtherImageObject Detection

Applied machine learning to identify biomarkers and performed image processing with ML-based feature extraction to support disease biomarker discovery. The role used ML to generate interpretable features from image-derived inputs for biomarker-related modeling. • Identified biomarkers for cardiovascular and liver diseases using machine learning • Applied image processing and ML-based feature extraction • Integrated ML-derived features into disease biomarker workflows • Supported ongoing analytics for therapeutic discovery programs

2025 - Present

Computational Scientist, Merck (Hybrid)

OtherClassification

Implemented large-scale RNA-seq and single-cell RNA-seq computational pipelines to transform biological assay outputs into analysis-ready datasets. The work supported downstream model-based discovery by generating processed data representations and applying standard statistical/modeling procedures for omics inference. • Built RNA-seq pipelines in Python and R on cloud and local environments • Built scRNA-seq pipelines using Scanpy and Seurat on AWS and local systems • Implemented proteomics pipelines using LIMMA and DEP • Conducted metabolomics and Drugseq analyses using R and Python

2024 - 2025

Chief Computational Officer & Cofounder, Organicin Scientific (Part-time)

AWS SageMakerTextPrompt + Response Writing (SFT)

Deployed and trained large-language-model workflows on proprietary peptide sequences for downstream classification and sequence improvement recommendations. The work included preparing model inputs/outputs for prompt-based use and building CI/CD-backed inference pipelines on cloud infrastructure. • LLM training on proprietary peptide sequences for classification • Sequence improvement recommendation generation • Prompt engineering/LLM workflow deployment on AWS • Integrated CI/CD for model deployment and updates

2023 - 2025

Chief Scientific Officer & Cofounder, zebraMD (Part-time)

OtherTextQuestion Answering

Built machine-learning systems to predict rare disease diagnoses and developed an automated RAG platform for generating disease brief text. The role focused on converting user queries and retrieved knowledge into structured natural-language outputs for clinical-style summaries. • ML diagnosis prediction for rare diseases • Built prompt engineering-based RAG for disease blurb synthesis • Automated text generation conditioned on retrieved content • Iterated model prompts for improved summary outputs

2023 - 2024

Data Science Fellow, Springboard (Remote)

Don't discloseTextText Generation

Applied neural networks and machine-learning models for supervised and unsupervised classification/regression tasks on provided datasets. Produced an NLP-based text-to-video cartoon generation system, requiring creation of multimodal training inputs (text and imagery) and model-based generation outputs. • Performed data wrangling, EDA, and visualization for ML projects • Built supervised/unsupervised models for classification/regression • Nominated transcriptomic biomarkers using elastic net, NMF, and PCA • Developed text-to-video cartoon generation using NLP and deep learning

2022 - 2024

Show more

Education

Work History